7 papers
Layer barriers for colour-biased tight Hamilton cycles
Zijian Deng, Qinfei Tang, Caihong Yang
We construct a family of layer barriers for colour-biased tight Hamilton cycles in uniform hypergraphs. For every and every , we give a red--blue col…
Blind-Spots-Bench: Evaluating Blind Spots in Multimodal Models
Matteo Santelmo, Xiuying Wei, Israa Fakih +5
Modern AI models achieve strong performance on many established benchmarks, yet they still fail on tasks that humans find almost trivial, such as manipulating a string or drawing a…
MyoChallenge 2025: A New Benchmark for Human Athletic Intelligence
Cheryl Wang, Chun Kwang Tan, Balint K. Hodossy +21
Athletic performance represents the pinnacle of human motor intelligence, demanding rapid choices, precise control, agility, and coordinated physical execution. Replicating this se…
Towards Embodied AI with MuscleMimic: Unlocking full-body musculoskeletal motor learning at scale
Chengkun Li, Cheryl Wang, Bianca Ziliotto +4
Learning motor control for muscle-driven musculoskeletal models is hindered by the computational cost of biomechanically accurate simulation and the scarcity of validated, open ful…
Arnold: A multi-task, multi-embodiment muscle transformer policy
Alberto Silvio Chiappa, Boshi An, Merkourios Simos +2
Controlling high-dimensional and nonlinear musculoskeletal models of the human body is a foundational scientific challenge. Recent machine learning breakthroughs have heralded in-s…
InkSight: Offline-to-Online Handwriting Conversion by Teaching Vision-Language Models to Read and Write
Blagoj Mitrevski, Arina Rak, Julian Schnitzler +4
Digital note-taking is gaining popularity, offering a durable, editable, and easily indexable way of storing notes in a vectorized form, known as digital ink. However, a substantia…